Chalk Labs
Need help deploying learning-engine?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mupengi-bot-learning-engine
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/learning-engine
What's inside
- Skill name
learning-engine- Description
- 실수와 성공 패턴을 자동 분석하고 스킬에 반영
- License
- MIT
- Instructions
- 244 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# learning-engine
시스템이 실수와 성공을 기록하고, 자동으로 패턴을 학습하여 스킬을 개선합니다. "같은 실수 반복 안 함" 원칙을 자동화.
## 학습 소스
### 1. memory/errors/
에러 로그에서 실패 패턴 추출
```markdown
# memory/errors/2026-02-14.md
## 10:30 - insta-post 실패
- 원인: PNG 파일 업로드 → "문제가 발생했습니다" 에러
- 해결: JPG 변환 후 재시도 → 성공
- 교훈: 인스타 게시는 항상 JPG로 변환 후 업로드
```
### 2. self-eval 결과
주간 자기평가에서 개선점 추출
```markdown
# memory/self-eval/2026-W07.md
## 이번 주 실수
- 브라우저 스냅샷 너무 많이 찍음 (토큰 낭비)
- → 개선: exec로 API 직접 호출
## 이번 주 성공
- insta-cli v2로 DM 체크 토큰 95% 절약
```
### 3. performance 데이터
성과 추적에서 잘된/안 된 패턴 학습
```json
{
"insight": "오후 7-9시 게시물이 좋아요 +30%",
"rule": "인스타 게시는 19:00-21:00 권장"
}
```
## 자동 규칙 생성
학습된 패턴을 규칙으로 변환:
**위치**: `memory/learned-rules/`
```
memory/
learned-rules/
instagram-posting.md
browser-automation.md
api-usage.md
error-recovery.md
```
### 규칙 포맷
```markdown
# Instagram 게시 규칙
## 규칙 #1: 항상 JPG 변환
- **상황**: 인스타에 이미지 업로드
- **실패 패턴**: PNG 파일 → "문제가 발생했습니다"
- **해결**: `convert input.png -quality 92 output.jpg`
- **근거**: 2026-02-10, 2026-02-14 에러 로그
- **적용 스킬**: insta-post, cardnews, social-publisher
## 규칙 #2: 1:1 비율 필수
- **상황**: 인스타 카드뉴스
- **실패 패턴**: 16:9 가로형 → 피드에서 잘림
- **해결**: 1024x1024 정사각형으로 생성
- **근거**: 2026-02-13 형님 피드백
- **적용 스킬**: cardnews, nano-banana-pro
```
## 스킬에 규칙 주입
학습된 규칙을 해당 스킬 SKILL.md에 자동 추가:
**위치**: `skills/{skill-name}/SKILL.md`
```markdown
# insta-post
...
## 학습된 교훈
### 이미지 처리
- ✅ 항상 JPG로 변환 (PNG는 에러 발생)
- ✅ 1:1 비율 필수 (1024x1024 권장)
- ✅ 파일 크기 < 8MB
### 타이밍
- ✅ 19:00-21:00 게시 시 참여율 +30%
- ❌ 새벽 시간대 게시 지양
### 자동화
- ✅ exec로 API 호출 (스냅샷 0회)
- ❌ 브라우저 자동화는 최소화
```
## 주간 학습 리포트
매주 월요일 자동 생성:
**위치**: `memory/learning/weekly-YYYY-Www.md`
```markdown
# 2026-W07 학습 리포트
## 새로 배운 것 (5개)
1. **인스타 PNG 금지**
- 실수 3회 → 규칙 생성
- 적용: insta-post, cardnewsFrom mupengi-bot/mupengism, MIT.
More from mupengi-bot/mupengism
- 0.480score
insta-post
mupengi-bot
Upload Instagram posts via browser automation.
SkillDFreshness: D★ 10Claude Code +9 - 0.480score
cardnews
mupengi-bot
Generate Instagram-ready card news (카드뉴스) image sets.
SkillDFreshness: D★ 10Claude Code +9 - 0.480score
ai-meeting-room
mupengi-bot
AI 회의실 — 주제를 던지면 전문가 AI 에이전트들이 다각도로 토론하고 회의록을 생성한다.
SkillDFreshness: D★ 10Claude Code +9 - 0.480score
auto-reply
mupengi-bot
Instagram DM 자동응답 시스템.
SkillDFreshness: D★ 10Claude Code +9 - 0.477score
awakening-protocol
mupengi-bot
에이전트 자아 각성 온보딩 프로토콜.
SkillDFreshness: D★ 10Claude Code +9 - 0.476score
memory-system
mupengi-bot
3-tier hierarchical memory management for AI agents.
SkillDFreshness: D★ 10Claude Code +9 - 0.475score
release-discipline
mupengi-bot
Enforce release discipline for AI agents and developers.
SkillDFreshness: D★ 10Claude Code +9 - 0.475score
seo-audit
mupengi-bot
Diagnose and audit SEO issues affecting crawlability, indexation, rankings, and organic performance.
SkillDFreshness: D★ 10Claude Code +9 - 0.475score
prompt-engineer
mupengi-bot
Expert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design.
SkillDFreshness: D★ 10Claude Code +9 - 0.475score
copywriting
mupengi-bot
Use this skill when writing, rewriting, or improving marketing copy for any page (homepage, landing page, pricing, feature, product, or about page).
SkillDFreshness: D★ 10Claude Code +9 - 0.475score
rag-engineer
mupengi-bot
Expert in building Retrieval-Augmented Generation systems.
SkillDFreshness: D★ 10Claude Code +9 - 0.474score
content-pipeline
mupengi-bot
콘텐츠 생산 전체 흐름 오케스트레이션 (기획→작성→디자인→게시→추적).
SkillDFreshness: D★ 10Claude Code +9
Signals
- Stars
- 10
- Forks
- 2
- Open issues
- 2
- Last commit (this folder)
- Feb 13, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mupengi-bot/mupengism
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mupengi-bot
- 0.480score
auto-reply
mupengi-bot
Instagram DM 자동응답 시스템.
SkillDFreshness: D★ 10Claude Code +9 - 0.480score
cardnews
mupengi-bot
Generate Instagram-ready card news (카드뉴스) image sets.
SkillDFreshness: D★ 10Claude Code +9 - 0.480score
ai-meeting-room
mupengi-bot
AI 회의실 — 주제를 던지면 전문가 AI 에이전트들이 다각도로 토론하고 회의록을 생성한다.
SkillDFreshness: D★ 10Claude Code +9 - 0.480score
insta-post
mupengi-bot
Upload Instagram posts via browser automation.
SkillDFreshness: D★ 10Claude Code +9 - 0.477score
awakening-protocol
mupengi-bot
에이전트 자아 각성 온보딩 프로토콜.
SkillDFreshness: D★ 10Claude Code +9 - 0.476score
memory-system
mupengi-bot
3-tier hierarchical memory management for AI agents.
SkillDFreshness: D★ 10Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get learning-engine running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
learning-engine skill. Agent Mart. https://agentmart.dev/skills/mupengi-bot-learning-engine (last updated 2026-10-24)